Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2410.08188 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913540462346240 |
|---|---|
| author | He, Mingming Clausen, Pascal Taşel, Ahmet Levent Ma, Li Pilarski, Oliver Xian, Wenqi Rikker, Laszlo Yu, Xueming Burgert, Ryan Yu, Ning Debevec, Paul |
| author_facet | He, Mingming Clausen, Pascal Taşel, Ahmet Levent Ma, Li Pilarski, Oliver Xian, Wenqi Rikker, Laszlo Yu, Xueming Burgert, Ryan Yu, Ning Debevec, Paul |
| contents | We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation. Leveraging a subject-specific dataset containing diverse facial expressions captured under various lighting conditions, including flat-lit and one-light-at-a-time (OLAT) scenarios, we train a diffusion model for precise lighting control, enabling high-fidelity relit facial images from flat-lit inputs. Our framework includes spatially-aligned conditioning of flat-lit captures and random noise, along with integrated lighting information for global control, utilizing prior knowledge from the pre-trained Stable Diffusion model. This model is then applied to dynamic facial performances captured in a consistent flat-lit environment and reconstructed for novel-view synthesis using a scalable dynamic 3D Gaussian Splatting method to maintain quality and consistency in the relit results. In addition, we introduce unified lighting control by integrating a novel area lighting representation with directional lighting, allowing for joint adjustments in light size and direction. We also enable high dynamic range imaging (HDRI) composition using multiple directional lights to produce dynamic sequences under complex lighting conditions. Our evaluations demonstrate the models efficiency in achieving precise lighting control and generalizing across various facial expressions while preserving detailed features such as skintexture andhair. The model accurately reproduces complex lighting effects like eye reflections, subsurface scattering, self-shadowing, and translucency, advancing photorealism within our framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08188 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DifFRelight: Diffusion-Based Facial Performance Relighting He, Mingming Clausen, Pascal Taşel, Ahmet Levent Ma, Li Pilarski, Oliver Xian, Wenqi Rikker, Laszlo Yu, Xueming Burgert, Ryan Yu, Ning Debevec, Paul Computer Vision and Pattern Recognition Artificial Intelligence Graphics We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation. Leveraging a subject-specific dataset containing diverse facial expressions captured under various lighting conditions, including flat-lit and one-light-at-a-time (OLAT) scenarios, we train a diffusion model for precise lighting control, enabling high-fidelity relit facial images from flat-lit inputs. Our framework includes spatially-aligned conditioning of flat-lit captures and random noise, along with integrated lighting information for global control, utilizing prior knowledge from the pre-trained Stable Diffusion model. This model is then applied to dynamic facial performances captured in a consistent flat-lit environment and reconstructed for novel-view synthesis using a scalable dynamic 3D Gaussian Splatting method to maintain quality and consistency in the relit results. In addition, we introduce unified lighting control by integrating a novel area lighting representation with directional lighting, allowing for joint adjustments in light size and direction. We also enable high dynamic range imaging (HDRI) composition using multiple directional lights to produce dynamic sequences under complex lighting conditions. Our evaluations demonstrate the models efficiency in achieving precise lighting control and generalizing across various facial expressions while preserving detailed features such as skintexture andhair. The model accurately reproduces complex lighting effects like eye reflections, subsurface scattering, self-shadowing, and translucency, advancing photorealism within our framework. |
| title | DifFRelight: Diffusion-Based Facial Performance Relighting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2410.08188 |